Predicting the Risk Factors Associated With Severe Outcomes Among COVID-19 Patients–Decision Tree Modeling Approach

Frontiers in Public Health

article

Mahalakshmi Kumaran¹  Truong-Minh Pham²  Kaiming Wang³  Hussain Usman¹  Colleen M. Norris⁵  Judy MacDonald⁷  Gavin Y. Oudit³  Vineet Saini⁹  Khokan C. Sikdar¹ 

[1] Surveillance and Reporting, Provincial Population and Public Health, Alberta Health Services;Surveillance and Reporting, Cancer Research and Analytics, Cancer Care Alberta, Alberta Health Services;Division of Cardiology, Department of Medicine, University of Alberta;Mazankowski Alberta Heart Institute, Faculty of Medicine and Dentistry, University of Alberta;Faculty of Nursing, University of Alberta;Cardiovascular Health and Stroke Strategic Clinical Network, Alberta Health Services;Department of Community Health Sciences, Cumming School of Medicine, University of Calgary;Communicable Disease Control, Provincial Population and Public Health, Alberta Health Services;Department of Community Health Sciences and O'Brien Institute for Public Health, Cumming School of Medicine, University of Calgary;Public Health Evidence and Innovation, Provincial Population and Public Health, Alberta Health Services

关键词: COVID-19;    SARS-CoV-2;    decision tree modeling;    machine learning;    outcome;   

DOI  :  10.3389/fpubh.2022.838514

学科分类：社会科学、人文和艺术（综合）

来源: Frontiers

【 摘 要 】

Background The COVID-19 pandemic has seen a large surge in case numbers over several waves, and has critically strained the health care system, with a significant number of cases requiring hospitalization and ICU admission. This study used a decision tree modeling approach to identify the most important predictors of severe outcomes among COVID-19 patients. Methods We identified a retrospective population-based cohort ( n = 140,182) of adults who tested positive for COVID-19 between 5 th March 2020 and 31 st May 2021. Demographic information, symptoms and co-morbidities were extracted from a communicable disease and outbreak management information system and electronic medical records. Decision tree modeling involving conditional inference tree and random forest models were used to analyze and identify the key factors(s) associated with severe outcomes (hospitalization, ICU admission and death) following COVID-19 infection. Results In the study cohort, nearly 6.37% were hospitalized, 1.39% were admitted to ICU and 1.57% died due to COVID-19. Older age (>71Y) and breathing difficulties were the top two factors associated with a poor prognosis, predicting about 50% of severe outcomes in both models. Neurological conditions, diabetes, cardiovascular disease, hypertension, and renal disease were the top five pre-existing conditions that altogether predicted 29% of outcomes. 79% of the cases with poor prognosis were predicted based on the combination of variables. Age stratified models revealed that among younger adults (18–40 Y), obesity was among the top risk factors associated with adverse outcomes. Conclusion Decision tree modeling has identified key factors associated with a significant proportion of severe outcomes in COVID-19. Knowledge about these variables will aid in identifying high-risk groups and allocating health care resources.

【 授权许可】

CC BY